Pagecraft

Name a PDF from its contents

Read the first pages of a document and propose what the file should be called.

What this does

“scan_0042.pdf” is what a scanner calls an invoice, and a folder of two hundred of them is a folder nobody can find anything in. The document knows what it is: it has a date on it, a party, a subject, usually in the first half page. So the first pages are read and a name is proposed. It proposes, and nothing here renames anything — the name is the one thing about a file its owner has an opinion on.

What it will not do

Every tool here says what it cannot do, in its own words, before you rely on it.

Questions people ask

Does it rename my file?

No. It proposes a name and shows it to you. Renaming is yours to do, on your own machine, with the name you actually want.

Can I choose how the name is built?

Yes — say what the parts should be and in what order. Anything the document does not supply is left out rather than guessed at.

What exactly is sent to the provider?

The text on the screen under “what will be sent”, and nothing else of your document. It is not a summary of the request — it is the request. Nothing is sent until you press send, and the page cannot send it before showing it to you, because the code refuses.

What does this cost?

Pagecraft charges nothing and never will. Your provider charges you for what you send it, at their rates, on your own account — and you are shown the token count and an estimate in dollars before you send anything. A model on your own machine costs nothing at all.

Do I have to pay for an API key?

No. Install Ollama or LM Studio, run a model on your own computer, and point Pagecraft at it: no key, no bill, and your document never leaves the device. That path is first-class here rather than a degraded fallback.